Convolutional neural network (CNN) has been widely applied in the field of handwritten numeral recognition, but the discuss about the parameter of CNN network structure is pretty few. This paper made in-depth analysis of CNN network systematically and make in-depth research on network structure, the number of hidden feature map, the size of convolutional kernel, weight initialization, the number of bulk samples, iteration times and other parameters in recognition process and provide their value choice method. This paper also proposed a method based on CNN analysis and experiment and optimized the parameters of CNN aimed for MNIST handwritten numeral database. In addition, this paper proposed the process and method applied in handwritten numeral parameter optimization based on CNN image recognition, which has a good reference value for the further application of CNN network in the field of image recognition.
Abstract-As the main component of intelligent transportation systems, Traffic sign recognition system has been extensively studied in intelligent vehicles, military and unmanned vehicles and other projects. In this paper, firstly, it briefly introduced the traffic sign recognition research status and development background, and then according to different recognition review,it mainstreamd traffic sign recognition method, through comparative analysis of various methods,it summarized the in traffic sign recognition, and prospected the future direction of development.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.